Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses the mark_read side effect ('Set mark_read:true to flag returned events read so the next call only shows newer ones'), which directly contradicts the readOnlyHint=true annotation. Since the description describes a mutating operation while annotations claim read-only, this is a clear annotation contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is four sentences, front-loaded with the core action, and each sentence adds distinct value: return fields, filtering, mark_read behavior, and alternative access. No redundant or filler content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple 5-parameter schema and presence of annotations, the description covers purpose, return payload, filtering, read-state behavior, and even provides an alternative HTTP endpoint. It doesn't elaborate on limit/unread_only, but those are fully documented in the schema. Overall quite complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although the schema covers all 5 parameters, the description adds value by giving a concrete type example ('sec_8k'), clarifying the ISO timestamp format for 'since', and explaining the mark_read semantic in terms of subsequent calls. This goes beyond the schema's descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Pull fired events from your subscription feed' and 'Returns the most recent alerts the evaluator has written to your persisted feed'. It distinguishes itself from sibling tools like list_subscriptions and recent_changes by focusing specifically on fired alerts from the persisted feed.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides usage context, noting that 'Polls work fine' and gives an alternative HTTP endpoint for scripts/dashboards. It also explains filtering by type and since, and the mark_read behavior for advancing the feed. However, it doesn't explicitly contrast with sibling MCP tools or state when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.